kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (370) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +538 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +4 -104
  8. data/README.md +454 -432
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -341
  12. data/ext/kreuzberg_rb/extconf.rb +45 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
  14. data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
  15. data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3135
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -182
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -46
  27. data/lib/kreuzberg/cli.rb +55 -55
  28. data/lib/kreuzberg/cli_proxy.rb +127 -127
  29. data/lib/kreuzberg/config.rb +724 -724
  30. data/lib/kreuzberg/error_context.rb +80 -32
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  36. data/lib/kreuzberg/result.rb +279 -279
  37. data/lib/kreuzberg/setup_lib_path.rb +80 -80
  38. data/lib/kreuzberg/validator_protocol.rb +89 -89
  39. data/lib/kreuzberg/version.rb +5 -5
  40. data/lib/kreuzberg.rb +109 -103
  41. data/lib/pdfium.dll +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -537
  44. data/spec/binding/cache_spec.rb +227 -227
  45. data/spec/binding/cli_proxy_spec.rb +85 -85
  46. data/spec/binding/cli_spec.rb +55 -55
  47. data/spec/binding/config_spec.rb +345 -345
  48. data/spec/binding/config_validation_spec.rb +283 -283
  49. data/spec/binding/error_handling_spec.rb +213 -213
  50. data/spec/binding/errors_spec.rb +66 -66
  51. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  52. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  53. data/spec/binding/plugins/validator_spec.rb +274 -274
  54. data/spec/fixtures/config.toml +39 -39
  55. data/spec/fixtures/config.yaml +41 -41
  56. data/spec/fixtures/invalid_config.toml +4 -4
  57. data/spec/smoke/package_spec.rb +178 -178
  58. data/spec/spec_helper.rb +42 -42
  59. data/vendor/Cargo.toml +45 -0
  60. data/vendor/kreuzberg/Cargo.toml +61 -38
  61. data/vendor/kreuzberg/README.md +230 -221
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +843 -891
  64. data/vendor/kreuzberg/src/api/error.rs +81 -81
  65. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  66. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  67. data/vendor/kreuzberg/src/api/server.rs +353 -353
  68. data/vendor/kreuzberg/src/api/types.rs +170 -170
  69. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  70. data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
  71. data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
  72. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  73. data/vendor/kreuzberg/src/core/config.rs +1080 -1080
  74. data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
  75. data/vendor/kreuzberg/src/core/io.rs +329 -329
  76. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  77. data/vendor/kreuzberg/src/core/mod.rs +47 -47
  78. data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -432
  80. data/vendor/kreuzberg/src/error.rs +431 -431
  81. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  82. data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
  83. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  84. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  85. data/vendor/kreuzberg/src/extraction/html.rs +601 -569
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
  88. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
  89. data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
  90. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  91. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  92. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  93. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  94. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
  95. data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
  96. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  97. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  98. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  99. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  100. data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
  101. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
  102. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
  103. data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
  104. data/vendor/kreuzberg/src/extractors/email.rs +157 -157
  105. data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
  106. data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
  107. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
  108. data/vendor/kreuzberg/src/extractors/html.rs +407 -407
  109. data/vendor/kreuzberg/src/extractors/image.rs +219 -219
  110. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
  112. data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
  114. data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
  115. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  116. data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
  117. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
  118. data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
  119. data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
  120. data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
  121. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
  122. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  123. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  124. data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
  125. data/vendor/kreuzberg/src/extractors/text.rs +265 -265
  126. data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
  127. data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
  128. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  129. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  130. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  131. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  132. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  133. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  134. data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
  135. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  136. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  137. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  138. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
  139. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
  140. data/vendor/kreuzberg/src/lib.rs +113 -113
  141. data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
  142. data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
  143. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  144. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  145. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  146. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  147. data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
  148. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  149. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  150. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
  151. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  152. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  153. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  154. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  155. data/vendor/kreuzberg/src/pdf/bindings.rs +44 -0
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
  157. data/vendor/kreuzberg/src/pdf/error.rs +130 -130
  158. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  159. data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
  160. data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -417
  163. data/vendor/kreuzberg/src/pdf/text.rs +240 -240
  164. data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
  165. data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
  166. data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
  167. data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
  168. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
  169. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  170. data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
  171. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  172. data/vendor/kreuzberg/src/text/mod.rs +25 -25
  173. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  174. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
  175. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  176. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  177. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  178. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  179. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  180. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  181. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  182. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  183. data/vendor/kreuzberg/src/types.rs +1055 -1055
  184. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  185. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  186. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  187. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  188. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  189. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  190. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  191. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  192. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  193. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  194. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  195. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  196. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  198. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  199. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  200. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  201. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  202. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  203. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  204. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  205. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  206. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  207. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  208. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  209. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  210. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  211. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  212. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  213. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  214. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  215. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  216. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  217. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  218. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  219. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  220. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  221. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  222. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  223. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  224. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  225. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  226. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  227. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  228. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  229. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  230. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  231. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  232. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  233. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  234. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  235. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  236. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  237. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  238. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  239. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  240. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  241. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  242. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  243. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  244. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  245. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  246. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  247. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  248. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  249. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  250. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  251. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  252. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  253. data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
  254. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
  255. data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
  256. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  257. data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
  258. data/vendor/kreuzberg/tests/config_features.rs +612 -612
  259. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
  260. data/vendor/kreuzberg/tests/core_integration.rs +510 -510
  261. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  262. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
  263. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  264. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  265. data/vendor/kreuzberg/tests/email_integration.rs +327 -327
  266. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  267. data/vendor/kreuzberg/tests/error_handling.rs +402 -402
  268. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  269. data/vendor/kreuzberg/tests/format_integration.rs +164 -161
  270. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  271. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  272. data/vendor/kreuzberg/tests/image_integration.rs +255 -255
  273. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  274. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  275. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  276. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  277. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  278. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  279. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  280. data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
  281. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
  282. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
  283. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
  284. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  285. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
  286. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  287. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  288. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
  289. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
  290. data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
  291. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
  292. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
  293. data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
  294. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  295. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
  296. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
  297. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
  298. data/vendor/kreuzberg/tests/security_validation.rs +416 -416
  299. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  300. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
  301. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
  302. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
  303. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  304. data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
  305. data/vendor/kreuzberg-ffi/README.md +851 -0
  306. data/vendor/kreuzberg-ffi/build.rs +176 -0
  307. data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
  308. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
  309. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  310. data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
  311. data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
  312. data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -0
  313. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  314. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  315. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  316. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  317. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  318. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  319. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  320. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  321. data/vendor/kreuzberg-tesseract/Cargo.toml +48 -0
  322. data/vendor/kreuzberg-tesseract/LICENSE +22 -0
  323. data/vendor/kreuzberg-tesseract/README.md +399 -0
  324. data/vendor/kreuzberg-tesseract/build.rs +1354 -0
  325. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  326. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  327. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  328. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  329. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  330. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  331. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  332. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  333. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  334. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  335. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  336. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  337. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  338. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  339. data/vendor/rb-sys/Cargo.lock +393 -393
  340. data/vendor/rb-sys/Cargo.toml +70 -70
  341. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  342. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  343. data/vendor/rb-sys/LICENSE-MIT +21 -21
  344. data/vendor/rb-sys/build/features.rs +111 -111
  345. data/vendor/rb-sys/build/main.rs +286 -286
  346. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  347. data/vendor/rb-sys/build/version.rs +50 -50
  348. data/vendor/rb-sys/readme.md +36 -36
  349. data/vendor/rb-sys/src/bindings.rs +21 -21
  350. data/vendor/rb-sys/src/hidden.rs +11 -11
  351. data/vendor/rb-sys/src/lib.rs +35 -35
  352. data/vendor/rb-sys/src/macros.rs +371 -371
  353. data/vendor/rb-sys/src/memory.rs +53 -53
  354. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  355. data/vendor/rb-sys/src/special_consts.rs +31 -31
  356. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  357. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  358. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  359. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  360. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  361. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  362. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  363. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  364. data/vendor/rb-sys/src/stable_api.rs +260 -260
  365. data/vendor/rb-sys/src/symbol.rs +31 -31
  366. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  367. data/vendor/rb-sys/src/utils.rs +89 -89
  368. data/vendor/rb-sys/src/value_type.rs +7 -7
  369. metadata +44 -81
  370. data/vendor/rb-sys/bin/release.sh +0 -21
@@ -1,89 +1,89 @@
1
- //! Internal utility functions.
2
-
3
- /// Check if the Ruby VM is globally available.
4
- ///
5
- /// Unfortunately there is no public API for this check, but there's a hidden
6
- /// `ruby_current_vm_ptr` symbol in libruby 2.5 - 3.2 which we can use to
7
- /// determine if the VM has been initialized, or shut down.
8
- ///
9
- /// # Notes
10
- ///
11
- /// Ruby 2.4 and below don't have a global VM pointer, so we can't check if it's
12
- /// null. Ruby 2.4 is EOL, and support will be dropped soon anyway.
13
- //
14
- /// In Ruby 3.3, the global VM pointer is no longer exported, so there's no
15
- /// simple way to check the global VM pointer, so instead we check if known
16
- /// static value is non-zero.
17
- ///
18
- /// On Ruby < 3.3, we also need to check if the global VM pointer is null to
19
- /// ensure the VM hasn't stopped, which makes the function name a bit of a
20
- /// misnomer... but in actuality this function can only guarantee that the
21
- /// VM is started, not that it's still running.
22
- #[allow(dead_code)]
23
- pub(crate) unsafe fn is_ruby_vm_started() -> bool {
24
- #[cfg(ruby_engine = "mri")]
25
- let ret = {
26
- #[cfg(all(ruby_gt_2_4, ruby_lte_3_2))]
27
- let ret = !crate::hidden::ruby_current_vm_ptr.is_null();
28
-
29
- #[cfg(any(ruby_lte_2_4, ruby_gt_3_2))]
30
- let ret = crate::rb_cBasicObject != 0;
31
-
32
- ret
33
- };
34
-
35
- #[cfg(ruby_engine = "truffleruby")]
36
- let ret = crate::rb_cBasicObject != 0;
37
-
38
- ret
39
- }
40
-
41
- /// Macro for conditionally asserting type checks in Ruby, only active when RUBY_DEBUG is enabled.
42
- /// This matches Ruby's behavior of only checking types in debug mode.
43
- #[macro_export]
44
- macro_rules! debug_ruby_assert_type {
45
- ($obj:expr, $type:expr, $message:expr) => {
46
- #[cfg(ruby_ruby_debug = "true")]
47
- {
48
- #[allow(clippy::macro_metavars_in_unsafe)]
49
- unsafe {
50
- assert!(
51
- !$crate::SPECIAL_CONST_P($obj) && $crate::RB_BUILTIN_TYPE($obj) == $type,
52
- $message
53
- );
54
- }
55
- }
56
- #[cfg(not(ruby_ruby_debug = "true"))]
57
- {
58
- let _ = ($obj, $type, $message); // Prevent unused variable warnings
59
- }
60
- };
61
- }
62
-
63
- #[cfg(test)]
64
- mod tests {
65
- use super::*;
66
- use rusty_fork::rusty_fork_test;
67
-
68
- rusty_fork_test! {
69
- #[test]
70
- fn test_is_ruby_vm_started() {
71
- assert!(!unsafe { is_ruby_vm_started() });
72
-
73
- #[cfg(windows)]
74
- {
75
- let mut argc = 0;
76
- let mut argv: [*mut std::os::raw::c_char; 0] = [];
77
- let mut argv = argv.as_mut_ptr();
78
- unsafe { rb_sys::rb_w32_sysinit(&mut argc, &mut argv) };
79
- }
80
-
81
- match unsafe { crate::ruby_setup() } {
82
- 0 => {}
83
- code => panic!("Failed to setup Ruby (error code: {})", code),
84
- };
85
-
86
- assert!(unsafe { is_ruby_vm_started() });
87
- }
88
- }
89
- }
1
+ //! Internal utility functions.
2
+
3
+ /// Check if the Ruby VM is globally available.
4
+ ///
5
+ /// Unfortunately there is no public API for this check, but there's a hidden
6
+ /// `ruby_current_vm_ptr` symbol in libruby 2.5 - 3.2 which we can use to
7
+ /// determine if the VM has been initialized, or shut down.
8
+ ///
9
+ /// # Notes
10
+ ///
11
+ /// Ruby 2.4 and below don't have a global VM pointer, so we can't check if it's
12
+ /// null. Ruby 2.4 is EOL, and support will be dropped soon anyway.
13
+ //
14
+ /// In Ruby 3.3, the global VM pointer is no longer exported, so there's no
15
+ /// simple way to check the global VM pointer, so instead we check if known
16
+ /// static value is non-zero.
17
+ ///
18
+ /// On Ruby < 3.3, we also need to check if the global VM pointer is null to
19
+ /// ensure the VM hasn't stopped, which makes the function name a bit of a
20
+ /// misnomer... but in actuality this function can only guarantee that the
21
+ /// VM is started, not that it's still running.
22
+ #[allow(dead_code)]
23
+ pub(crate) unsafe fn is_ruby_vm_started() -> bool {
24
+ #[cfg(ruby_engine = "mri")]
25
+ let ret = {
26
+ #[cfg(all(ruby_gt_2_4, ruby_lte_3_2))]
27
+ let ret = !crate::hidden::ruby_current_vm_ptr.is_null();
28
+
29
+ #[cfg(any(ruby_lte_2_4, ruby_gt_3_2))]
30
+ let ret = crate::rb_cBasicObject != 0;
31
+
32
+ ret
33
+ };
34
+
35
+ #[cfg(ruby_engine = "truffleruby")]
36
+ let ret = crate::rb_cBasicObject != 0;
37
+
38
+ ret
39
+ }
40
+
41
+ /// Macro for conditionally asserting type checks in Ruby, only active when RUBY_DEBUG is enabled.
42
+ /// This matches Ruby's behavior of only checking types in debug mode.
43
+ #[macro_export]
44
+ macro_rules! debug_ruby_assert_type {
45
+ ($obj:expr, $type:expr, $message:expr) => {
46
+ #[cfg(ruby_ruby_debug = "true")]
47
+ {
48
+ #[allow(clippy::macro_metavars_in_unsafe)]
49
+ unsafe {
50
+ assert!(
51
+ !$crate::SPECIAL_CONST_P($obj) && $crate::RB_BUILTIN_TYPE($obj) == $type,
52
+ $message
53
+ );
54
+ }
55
+ }
56
+ #[cfg(not(ruby_ruby_debug = "true"))]
57
+ {
58
+ let _ = ($obj, $type, $message); // Prevent unused variable warnings
59
+ }
60
+ };
61
+ }
62
+
63
+ #[cfg(test)]
64
+ mod tests {
65
+ use super::*;
66
+ use rusty_fork::rusty_fork_test;
67
+
68
+ rusty_fork_test! {
69
+ #[test]
70
+ fn test_is_ruby_vm_started() {
71
+ assert!(!unsafe { is_ruby_vm_started() });
72
+
73
+ #[cfg(windows)]
74
+ {
75
+ let mut argc = 0;
76
+ let mut argv: [*mut std::os::raw::c_char; 0] = [];
77
+ let mut argv = argv.as_mut_ptr();
78
+ unsafe { rb_sys::rb_w32_sysinit(&mut argc, &mut argv) };
79
+ }
80
+
81
+ match unsafe { crate::ruby_setup() } {
82
+ 0 => {}
83
+ code => panic!("Failed to setup Ruby (error code: {})", code),
84
+ };
85
+
86
+ assert!(unsafe { is_ruby_vm_started() });
87
+ }
88
+ }
89
+ }
@@ -1,7 +1,7 @@
1
- #![allow(rustdoc::broken_intra_doc_links)]
2
- //! Definitions for Ruby's special constants.
3
- //!
4
- //! Makes it easier to reference important Ruby constants, without havign to dig
5
- //! around in bindgen's output.
6
-
7
- pub use crate::ruby_value_type::*;
1
+ #![allow(rustdoc::broken_intra_doc_links)]
2
+ //! Definitions for Ruby's special constants.
3
+ //!
4
+ //! Makes it easier to reference important Ruby constants, without havign to dig
5
+ //! around in bindgen's output.
6
+
7
+ pub use crate::ruby_value_type::*;
metadata CHANGED
@@ -1,14 +1,13 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: kreuzberg
3
3
  version: !ruby/object:Gem::Version
4
- version: 4.0.0.pre.rc.8
4
+ version: 4.0.0.pre.rc.13
5
5
  platform: ruby
6
6
  authors:
7
7
  - Na'aman Hirschfeld
8
- autorequire:
9
8
  bindir: exe
10
9
  cert_chain: []
11
- date: 2025-12-14 00:00:00.000000000 Z
10
+ date: 2025-12-19 00:00:00.000000000 Z
12
11
  dependencies:
13
12
  - !ruby/object:Gem::Dependency
14
13
  name: bundler
@@ -80,76 +79,6 @@ dependencies:
80
79
  - - "~>"
81
80
  - !ruby/object:Gem::Version
82
81
  version: '3.12'
83
- - !ruby/object:Gem::Dependency
84
- name: rbs
85
- requirement: !ruby/object:Gem::Requirement
86
- requirements:
87
- - - "~>"
88
- - !ruby/object:Gem::Version
89
- version: '3.0'
90
- type: :development
91
- prerelease: false
92
- version_requirements: !ruby/object:Gem::Requirement
93
- requirements:
94
- - - "~>"
95
- - !ruby/object:Gem::Version
96
- version: '3.0'
97
- - !ruby/object:Gem::Dependency
98
- name: rubocop
99
- requirement: !ruby/object:Gem::Requirement
100
- requirements:
101
- - - "~>"
102
- - !ruby/object:Gem::Version
103
- version: '1.66'
104
- type: :development
105
- prerelease: false
106
- version_requirements: !ruby/object:Gem::Requirement
107
- requirements:
108
- - - "~>"
109
- - !ruby/object:Gem::Version
110
- version: '1.66'
111
- - !ruby/object:Gem::Dependency
112
- name: rubocop-performance
113
- requirement: !ruby/object:Gem::Requirement
114
- requirements:
115
- - - "~>"
116
- - !ruby/object:Gem::Version
117
- version: '1.21'
118
- type: :development
119
- prerelease: false
120
- version_requirements: !ruby/object:Gem::Requirement
121
- requirements:
122
- - - "~>"
123
- - !ruby/object:Gem::Version
124
- version: '1.21'
125
- - !ruby/object:Gem::Dependency
126
- name: rubocop-rspec
127
- requirement: !ruby/object:Gem::Requirement
128
- requirements:
129
- - - "~>"
130
- - !ruby/object:Gem::Version
131
- version: '3.0'
132
- type: :development
133
- prerelease: false
134
- version_requirements: !ruby/object:Gem::Requirement
135
- requirements:
136
- - - "~>"
137
- - !ruby/object:Gem::Version
138
- version: '3.0'
139
- - !ruby/object:Gem::Dependency
140
- name: steep
141
- requirement: !ruby/object:Gem::Requirement
142
- requirements:
143
- - - "~>"
144
- - !ruby/object:Gem::Version
145
- version: '1.8'
146
- type: :development
147
- prerelease: false
148
- version_requirements: !ruby/object:Gem::Requirement
149
- requirements:
150
- - - "~>"
151
- - !ruby/object:Gem::Version
152
- version: '1.8'
153
82
  - !ruby/object:Gem::Dependency
154
83
  name: yard
155
84
  requirement: !ruby/object:Gem::Requirement
@@ -214,6 +143,7 @@ files:
214
143
  - lib/kreuzberg/setup_lib_path.rb
215
144
  - lib/kreuzberg/validator_protocol.rb
216
145
  - lib/kreuzberg/version.rb
146
+ - lib/pdfium.dll
217
147
  - sig/kreuzberg.rbs
218
148
  - sig/kreuzberg/internal.rbs
219
149
  - spec/binding/cache_spec.rb
@@ -231,6 +161,41 @@ files:
231
161
  - spec/fixtures/invalid_config.toml
232
162
  - spec/smoke/package_spec.rb
233
163
  - spec/spec_helper.rb
164
+ - vendor/Cargo.toml
165
+ - vendor/kreuzberg-ffi/Cargo.toml
166
+ - vendor/kreuzberg-ffi/README.md
167
+ - vendor/kreuzberg-ffi/build.rs
168
+ - vendor/kreuzberg-ffi/cbindgen.toml
169
+ - vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc
170
+ - vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in
171
+ - vendor/kreuzberg-ffi/kreuzberg.h
172
+ - vendor/kreuzberg-ffi/src/lib.rs
173
+ - vendor/kreuzberg-ffi/src/panic_shield.rs
174
+ - vendor/kreuzberg-ffi/tests.disabled/README.md
175
+ - vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs
176
+ - vendor/kreuzberg-ffi/tests.disabled/config_tests.rs
177
+ - vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs
178
+ - vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs
179
+ - vendor/kreuzberg-tesseract/.commitlintrc.json
180
+ - vendor/kreuzberg-tesseract/.crate-ignore
181
+ - vendor/kreuzberg-tesseract/Cargo.lock
182
+ - vendor/kreuzberg-tesseract/Cargo.toml
183
+ - vendor/kreuzberg-tesseract/LICENSE
184
+ - vendor/kreuzberg-tesseract/README.md
185
+ - vendor/kreuzberg-tesseract/build.rs
186
+ - vendor/kreuzberg-tesseract/patches/README.md
187
+ - vendor/kreuzberg-tesseract/patches/tesseract.diff
188
+ - vendor/kreuzberg-tesseract/src/api.rs
189
+ - vendor/kreuzberg-tesseract/src/choice_iterator.rs
190
+ - vendor/kreuzberg-tesseract/src/enums.rs
191
+ - vendor/kreuzberg-tesseract/src/error.rs
192
+ - vendor/kreuzberg-tesseract/src/lib.rs
193
+ - vendor/kreuzberg-tesseract/src/monitor.rs
194
+ - vendor/kreuzberg-tesseract/src/mutable_iterator.rs
195
+ - vendor/kreuzberg-tesseract/src/page_iterator.rs
196
+ - vendor/kreuzberg-tesseract/src/result_iterator.rs
197
+ - vendor/kreuzberg-tesseract/src/result_renderer.rs
198
+ - vendor/kreuzberg-tesseract/tests/integration_test.rs
234
199
  - vendor/kreuzberg/Cargo.toml
235
200
  - vendor/kreuzberg/README.md
236
201
  - vendor/kreuzberg/benches/otel_overhead.rs
@@ -326,6 +291,7 @@ files:
326
291
  - vendor/kreuzberg/src/ocr/utils.rs
327
292
  - vendor/kreuzberg/src/ocr/validation.rs
328
293
  - vendor/kreuzberg/src/panic_context.rs
294
+ - vendor/kreuzberg/src/pdf/bindings.rs
329
295
  - vendor/kreuzberg/src/pdf/bundled.rs
330
296
  - vendor/kreuzberg/src/pdf/error.rs
331
297
  - vendor/kreuzberg/src/pdf/images.rs
@@ -480,7 +446,6 @@ files:
480
446
  - vendor/rb-sys/Cargo.toml.orig
481
447
  - vendor/rb-sys/LICENSE-APACHE
482
448
  - vendor/rb-sys/LICENSE-MIT
483
- - vendor/rb-sys/bin/release.sh
484
449
  - vendor/rb-sys/build/features.rs
485
450
  - vendor/rb-sys/build/main.rs
486
451
  - vendor/rb-sys/build/stable_api_config.rs
@@ -510,14 +475,13 @@ homepage: https://github.com/kreuzberg-dev/kreuzberg
510
475
  licenses:
511
476
  - MIT
512
477
  metadata:
513
- homepage_uri: https://github.com/kreuzberg-dev/kreuzberg
514
- source_code_uri: https://github.com/kreuzberg-dev/kreuzberg
478
+ bug_tracker_uri: https://github.com/kreuzberg-dev/kreuzberg/issues
515
479
  changelog_uri: https://github.com/kreuzberg-dev/kreuzberg/blob/main/CHANGELOG.md
516
480
  documentation_uri: https://docs.kreuzberg.dev
517
- bug_tracker_uri: https://github.com/kreuzberg-dev/kreuzberg/issues
518
- rubygems_mfa_required: 'true'
481
+ homepage_uri: https://github.com/kreuzberg-dev/kreuzberg
519
482
  keywords: document-intelligence,document-extraction,ocr,rust,bindings
520
- post_install_message:
483
+ rubygems_mfa_required: 'true'
484
+ source_code_uri: https://github.com/kreuzberg-dev/kreuzberg
521
485
  rdoc_options: []
522
486
  require_paths:
523
487
  - lib
@@ -532,8 +496,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
532
496
  - !ruby/object:Gem::Version
533
497
  version: '0'
534
498
  requirements: []
535
- rubygems_version: 3.5.22
536
- signing_key:
499
+ rubygems_version: 4.0.2
537
500
  specification_version: 4
538
501
  summary: High-performance document intelligence framework
539
502
  test_files: []
@@ -1,21 +0,0 @@
1
- #!/bin/bash
2
-
3
- set -euo pipefail
4
- IFS=$'\n\t'
5
-
6
- if ! git diff-index --quiet HEAD --; then
7
- echo "There are git changes, cannot release"
8
- exit 1
9
- fi
10
-
11
- read -rp "What version would you like to release? (current $(grep version Cargo.toml)): " version
12
- read -rp "Are you sure you want to bump to v$version? <y/N> " prompt
13
-
14
- if [[ $prompt =~ [yY](es)* ]]; then
15
- sed -i '' "s/^version = .*/version = \"$version\"/g" Cargo.toml
16
- cargo build
17
- git add Cargo.lock Cargo.toml ../../Cargo.lock
18
- git commit -am "Bump to v$version"
19
- git tag "v$version"
20
- git push --atomic origin main "v$version"
21
- fi